flâneur — a map of the web's best reading

Designing AI resistant technical evaluations \ Anthropic

anthropic.com · 2,674 words · saved by 1 readers

What we learned from three iterations of a performance engineering take-home that Claude keeps beating.

Written by Tristan Hume, a lead on Anthropic's performance optimization team. Tristan designed—and redesigned—the take-home test that's helped Anthropic hire dozens of performance engineers. Evaluating technical candidates becomes harder as AI capabilities improve. A take-home that distinguishes well between human skill levels today may be trivially solved by models tomorrow—rendering it useless for evaluation. Since early 2024, our performance engineering team has used a take-home test where candidates optimize code for a simulated accelerator. Over 1,000 candidates have completed it, and doz

Explore this link on the map →

related reading